Week 4: Existing Sleep Questionnaires

Mar 22, 2019

Hello everyone,

Since I’ve decided to focus on accessibility, I’ve been looking into existing sleep questionnaires that can be done online in order to know if one should go to the doctor for a sleep test. The four main sleep questionnaires that I studied are Berlin, Epworth Sleepiness Scale, STOP, and STOP-Bang. They all focus on various aspects of sleep. For example, the Epworth Sleepiness Scale focuses on and measures daytime sleepiness.

I was curious and I decided to answer these questionnaires to find my probability of having sleep apnea. This is when I noticed something a bit concerning. Many of these questionnaires ask me how loud I snore or how often I snore. In reality, I don’t know! I never thought I snored until a recent sleepover with my friends in which they told me that I do. This got me wondering: What if there was an app that recorded you while you slept and gave you the analytics such as how often you snored and how loud you snored? I spent time looking into the feasibility of that idea and how I could integrate it into my project. Guess what? I later realized that the app is already made and is called SnoreLab! Just another reminder to me about how fascinating and useful phone applications can be.

Anyways, I digress. I looked at interesting cross-sectional studies, such as one done by Dr. Hassan El-Sayed. He concluded that the Berlin, STOP, and STOP-Bang questionnaires had high sensitivity but the questions were of low specificity, which resulted in the exclusion of individuals at low risk of OSA (I’ll include the link for this study below). It makes me wonder if my tool should integrate a questionnaire. In the meanwhile, I’ll be looking for existing sleep analytics apps that may help me make my questions more specific than these older sleep questionnaires due to people now having access to phones.

It’ll be interesting to see and exciting to share. Meanwhile, I’ve been progressing to week 5 in my ML course.

Thank you,



One Reply to “Week 4: Existing Sleep Questionnaires”

  1. Sahil J. says:

    Great to hear that you’ve made progress on your course!

    I would be very interested to see a questionnaire integration into your training model. Perhaps, you could combine your sleep data and questionnaire data to train a model, and see how that compares to a model trained with just one of either questionnaire data and/or sleep data. The possibilities are vast 🙂

Leave a Reply

Your email address will not be published. Required fields are marked *